EXA add conditioned activation plot in multi_csc example #19

TomDLT · 2019-06-11T20:43:58Z

Here I add the event-related activation figure in the multi CSC example.
It is not as cool as the one we discussed, since this set of parameter does not decompose the ERP for events 3-4 into two atoms (see below).

jasmainak · 2019-06-11T23:12:45Z

examples/multicsc/plot_sample_evoked_response.py

+this_info['events'] = events
+
+plot_epochs_of_selected_atoms(cdl, z_hat, X, this_info, t_lim, idx_atoms,
+                              channel=channel, align=False)


what are the different colors in the third subplot? do you show both the activations and reconstructed signal?

Third row:

Dots are the activations, same colors as fourth row (the dot is not the activation onset but the time at its maximum absolute value).

Reds and Blues are the reconstructed signals, same colormap and vmin/vmax as first row.

examples/multicsc/plot_sample_evoked_response.py

codecov-io · 2019-06-12T02:11:32Z

Codecov Report

Merging #19 into master will decrease coverage by 0.23%.
The diff coverage is 11.11%.

@@            Coverage Diff             @@
##           master      #19      +/-   ##
==========================================
- Coverage   81.75%   81.51%   -0.23%     
==========================================
  Files          23       23              
  Lines        2290     2299       +9     
==========================================
+ Hits         1872     1874       +2     
- Misses        418      425       +7

agramfort

you need to make sure that API page is up to date:

https://alphacsc.github.io/api.html

any public function in an example should be in the API page

agramfort · 2019-06-12T06:31:58Z

examples/multicsc/plot_sample_evoked_response.py

+# but displays the signal reconstructed using the two selected atoms. Colored
+# dots are present where each atom is activated. The last row depicts
+# histograms of activations for the selected atoms.
+from alphacsc.viz.epoch import plot_epochs_of_selected_atoms


Suggested change

from alphacsc.viz.epoch import plot_epochs_of_selected_atoms

from alphacsc.viz import plot_epochs_of_selected_atoms

agramfort · 2019-06-12T06:32:27Z

examples/multicsc/plot_sample_evoked_response.py

+# select the atoms to plot
+idx_atoms = [6, 30]
+
+this_info = deepcopy(info)


Suggested change

this_info = deepcopy(info)

this_info = info.copy()

should work

agramfort · 2019-06-12T06:33:46Z

examples/multicsc/plot_sample_evoked_response.py

@@ -222,7 +222,10 @@

 from alphacsc.utils.signal import fast_hilbert
 from alphacsc.viz.epoch import plot_evoked_surrogates


Suggested change

from alphacsc.viz.epoch import plot_evoked_surrogates

from alphacsc.viz import plot_evoked_surrogates

should work

agramfort · 2019-06-12T06:34:31Z

alphacsc/viz/epoch.py

+
+def plot_epochs_of_selected_atoms(model, z_hat, X_full, info, t_lim,
+                                  idx_atoms, channel=None,
+                                  align=False):


can you add a docstring

tomMoral

Some comments! this looks nice overall! Thanks @TomDLT :)

tomMoral · 2019-06-12T06:03:48Z

examples/multicsc/plot_sample_evoked_response.py

+# corresponds to a column. Then we pick the channel with the largest absolute
+# value in the spatial map of selected atoms. The top row displays the raw
+# timecourses on this channel, aligned on the event onsets, and ordered by
+# minimum raw value. The second row plots the average evoked timesourse,


Suggested change

# minimum raw value. The second row plots the average evoked timesourse,

# minimum raw value. The second row plots the average evoked time-course,

Also, you seem to be aligning based on the pred value and not on the raw value. something like:

# ... The top row displays the raw # time-courses on this channel, aligned on the event onsets, and ordered by # the localization of the minimum value of the signal reconstructed with the # two selected atoms.

tomMoral · 2019-06-12T06:05:03Z

examples/multicsc/plot_sample_evoked_response.py

+# value in the spatial map of selected atoms. The top row displays the raw
+# timecourses on this channel, aligned on the event onsets, and ordered by
+# minimum raw value. The second row plots the average evoked timesourse,
+# either on the raw signal or on the signal reconstructed using the two


Suggested change

# either on the raw signal or on the signal reconstructed using the two

# for both the raw signal and the signal reconstructed using the two

examples/multicsc/plot_sample_evoked_response.py

tomMoral · 2019-06-12T06:08:48Z

examples/multicsc/plot_sample_evoked_response.py

+# but displays the signal reconstructed using the two selected atoms. Colored
+# dots are present where each atom is activated. The last row depicts
+# histograms of activations for the selected atoms.
+from alphacsc.viz.epoch import plot_epochs_of_selected_atoms


I think we should add a comments on the usefulness of this representation. This captures some kind of latency in the signal and can be used to re-align the epochs before computing the evoked response?

tomMoral · 2019-06-12T06:20:04Z

alphacsc/viz/epoch.py

+
+def plot_epochs_of_selected_atoms(model, z_hat, X_full, info, t_lim,
+                                  idx_atoms, channel=None,
+                                  align=False):


A small docstring? :)

tomMoral · 2019-06-12T06:28:58Z

alphacsc/viz/epoch.py

+            ax.title.set_color(color)
+
+            # plot the event onsets in black
+            ax = axes[2 * ii, jj]


already done

Suggested change

ax = axes[2 * ii, jj]

tomMoral · 2019-06-12T06:32:20Z

alphacsc/viz/epoch.py

+            ax.legend()
+            ax.grid(True)
+
+            # plot the activations distributions


Maybe do not put it in the for-loop

tomMoral · 2019-06-12T06:32:44Z

examples/multicsc/plot_sample_evoked_response.py

-    v_k_1 = np.r_[[1], v_k][None]
-    z_k = z_hat[:, kk:kk + 1]
-    X_k = construct_X_multi(z_k, v_k_1, n_channels=1)[0, 0]
+    X_k = sources[kk]


tomMoral · 2019-06-12T06:33:06Z

examples/multicsc/plot_sample_evoked_response.py

@@ -264,6 +264,34 @@
 print("\rDisplayed {} atoms".format(len(plotted_atoms)).rjust(40))
 fig.tight_layout()

+###############################################################################
+# Here is a different visualization of the atoms correlated with the event


Suggested change

# Here is a different visualization of the atoms correlated with the event

# Here is a different visualization of some atoms correlated with the event

EXA add conditioned activation plot in multi_csc example

799d748

jasmainak reviewed Jun 11, 2019

View reviewed changes

examples/multicsc/plot_sample_evoked_response.py Outdated Show resolved Hide resolved

Update plot_sample_evoked_response.py

b025235

agramfort reviewed Jun 12, 2019

View reviewed changes

tomMoral reviewed Jun 12, 2019

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

EXA add conditioned activation plot in multi_csc example #19

EXA add conditioned activation plot in multi_csc example #19

TomDLT commented Jun 11, 2019 •

edited

jasmainak Jun 11, 2019

TomDLT Jun 12, 2019

codecov-io commented Jun 12, 2019

agramfort left a comment

agramfort Jun 12, 2019

agramfort Jun 12, 2019

agramfort Jun 12, 2019

agramfort Jun 12, 2019

tomMoral left a comment

tomMoral Jun 12, 2019

tomMoral Jun 12, 2019

tomMoral Jun 12, 2019

tomMoral Jun 12, 2019

tomMoral Jun 12, 2019

tomMoral Jun 12, 2019

tomMoral Jun 12, 2019

tomMoral Jun 12, 2019

	from alphacsc.viz.epoch import plot_epochs_of_selected_atoms
	from alphacsc.viz import plot_epochs_of_selected_atoms

		@@ -222,7 +222,10 @@

		from alphacsc.utils.signal import fast_hilbert
		from alphacsc.viz.epoch import plot_evoked_surrogates

	from alphacsc.viz.epoch import plot_evoked_surrogates
	from alphacsc.viz import plot_evoked_surrogates

	# minimum raw value. The second row plots the average evoked timesourse,
	# minimum raw value. The second row plots the average evoked time-course,

	# either on the raw signal or on the signal reconstructed using the two
	# for both the raw signal and the signal reconstructed using the two

	# Here is a different visualization of the atoms correlated with the event
	# Here is a different visualization of some atoms correlated with the event

EXA add conditioned activation plot in multi_csc example #19

Are you sure you want to change the base?

EXA add conditioned activation plot in multi_csc example #19

Conversation

TomDLT commented Jun 11, 2019 • edited

Choose a reason for hiding this comment

Choose a reason for hiding this comment

codecov-io commented Jun 12, 2019

Codecov Report

agramfort left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

tomMoral left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

TomDLT commented Jun 11, 2019 •

edited